I. INTRODUCTION
Computer vision systems mainly consider the recognition of 3D objects as a challenging of intelligent industries, medical field, robotic technologies and etc. In various industries, computer numerical control (CNC) machine is important in manufacturing process. CNC machine must operate at a fast pace, with accuracy and minimum error. Therefore, the object recognition is an important part of the machine tools that can work in intelligent system and prevent the errors which occurs with machine tools to quicken and increase accuracy. This system uses the images to analysis process by using the basic of image processing technique for detection the feature of the 2D-image. Type of images features include edges, corners, and interest points. These features are processed to help in segmentation and object recognition. The recognition for 2D images has many successful techniques but for 3D object recognition, it still has many problems to be solved. Neural network technology is used to provide effective methodologies for solving difficult computational problems in 3D recognition process [1].